Leaderboard bars
19 ranked models · higher is better
View accessible chart data
| Model | Rank | Provider | Score |
|---|---|---|---|
| Muse Spark 1.1 | #1 | Meta | 88.1% |
| Kimi K3 | #2 | Moonshot AI | 84.2% |
| Gemini 3.5 Flash | #3 | 83.6% | |
| Claude Opus 4.8 | #4 | Anthropic | 82.2% |
| Gemini 3.1 Pro Preview | #5 | 78.2% | |
| GLM-5.2 | #6 | Z.AI | 76.8% |
| Qwen3.7-Max | #7 | Alibaba Cloud | 76.4% |
| GPT-5.5 | #8 | OpenAI | 75.3% |
| MiniMax M3 | #9 | MiniMax | 74.2% |
| Qwen3.7-Plus | #10 | Alibaba Cloud | 73.2% |
| GLM-5.1 | #11 | Z.AI | 71.8% |
| GPT-5.4 | #12 | OpenAI | 70.6% |
| DeepSeek V4 Pro | #13 | DeepSeek | 69.4% |
| DeepSeek V4 Flash | #14 | DeepSeek | 64% |
| GPT-5.4 nano | #15 | OpenAI | 56.1% |
| Qwen3.6 Plus | #16 | Alibaba Cloud | 48.2% |
| Claude Opus 4.5 | #17 | Anthropic | 42.3% |
| GLM-5 | #18 | Z.AI | 31.1% |
| Kimi K2.5 | #19 | Moonshot AI | 29.5% |

